evals-first

What problem does it solve?

The 'evals-first' skill addresses the challenge of ensuring the correctness of prompt and skill logic in code that interacts with large language models (LLMs) before the actual implementation is made.

Core Features & Use Cases

• Eval-First Process: Ensures writing and testing evaluations before implementing the actual logic.
• LLM Interaction: Specifically designed for code that interacts with Claude Code sessions.
• Regression Coverage: Provides LLM-behavioral regression coverage, complementing traditional unit testing.
• Use Case: When a new feature is proposed that affects prompt logic or skill routing, this skill is activated to create and verify the evaluation before any implementation changes are made.

Quick Start

Load the 'evals-first' skill and write an evaluation that fails before you modify the prompt logic or skill in your code.